A framework for autonomous waypoint planning, trajectory generation through waypoints, and trajectory tracking for multi-rotor unmanned aerial vehicles (UAVs) is proposed in this work. Safe and effective operations of these UAVs is a problem that demands obstacle avoidance strategies
and advanced trajectory planning and control schemes for stability and energy efficiency. To address this problem, a two-level optimization strategy is used for trajectory generation, then the trajectory is tracked in a stable manner. The framework given here consists of the following components:
(a) a deep reinforcement learning (DRL)-based algorithm for optimal waypoint planning while minimizing control energy and avoiding obstacles in a given environment; (b) an optimal, smooth trajectory generation algorithm through waypoints, that minimizes a combinaton of velocity, acceleration, jerk and snap; and (c) a stable tracking control law that determines a control
thrust force for an UAV to track the generated trajectory.
more »
« less
This content will become publicly available on January 4, 2025
Mutual Information-Based Trajectory Planning for Cislunar Space Object Tracking using Successive Convexification.
We consider the problem of trajectory planning for optimal relative orbit determination in the cislunar environment. The recent interest in cislunar space has created a need to develop autonomous tracking technologies that can maintain situational awareness of this dynamically complex regime. Optical sensors provide an ideal observation platform because of their low cost and versatility in tracking both cooperative and non-cooperative space objects. The estimation performance of an optical observer can be significantly enhanced through manuevering. This work develops a trajectory planning tool, compatible with low-thrust propulsion, for tracking one or multiple targets operating in proximity to the observer. We formulate an objective function that is a convex combination of the mutual information between target states and measurements, and the low-thrust control effort. The subsequent optimal control problem is solved via direct collocation using the successive convexification algorithm, which, we argue, is well suited for a potential onboard trajectory planning application. We demonstrate the tool for several relevant scenarios with one and multiple targets operating around periodic orbits in the circular restricted three-body problem. A sequential estimator's performance is evaluated using the Cramer-Rao lower bound and, compared to a purely passive observer, we show that optimizing the observer's trajectory can decrease this bound by up to several orders of magnitude within a planning window. This investigation provides an initial proof-of-concept to future onboard planning technologies for relative tracking in the cislunar domain.
more »
« less
- Award ID(s):
- 2211548
- PAR ID:
- 10511434
- Publisher / Repository:
- American Institute of Aeronautics and Astronautics
- Date Published:
- Journal Name:
- AIAA SciTech Forum
- ISBN:
- 978-1-62410-711-5
- Format(s):
- Medium: X
- Location:
- Orlando, FL
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We address the problem of synthesizing a controller for nonlinear systems with reach-avoid requirements. Our controller consists of a reference controller and a tracking controller which drives the actual trajectory to follow the reference trajectory. We identify a type of reference trajectory such that the tracking error between the actual trajectory of the closed-loop system and the reference trajectory can be bounded. Moreover, such a bound on the tracking error is independent of the reference trajectory. Using such bounds on the tracking error, we propose a method that can find a reference trajectory by solving a satisfiability problem over linear constraints. Our overall algorithm guarantees that the resulting controller can make sure every trajectory from the initial set of the system satisfies the given reach-avoid requirement. We also implement our technique in a tool FACTEST. We show that FACTEST can find controllers for four vehicle models (3–6 dimensional state space and 2–4 dimensional input space) across eight scenarios (with up to 22 obstacles), all with running time at the sub-second range.more » « less
-
Unmanned aerial vehicle (UAV) technology is a rapidly growing field with tremendous opportunities for research and applications. To achieve true autonomy for UAVs in the absence of remote control, external navigation aids like global navigation satellite systems and radar systems, a minimum energy trajectory planning that considers obstacle avoidance and stability control will be the key. Although this can be formulated as a constrained optimization problem, due to the complicated non-linear relationships between UAV trajectory and thrust control, it is almost impossible to be solved analytically. While deep reinforcement learning is known for its ability to provide model free optimization for complex system through learning, its state space, actions and reward functions must be designed carefully. This paper presents our vision of different layers of autonomy in a UAV system, and our effort in generating and tracking the trajectory both using deep reinforcement learning (DRL). The experimental results show that compared to conventional approaches, the learned trajectory will need 20% less control thrust and 18% less time to reach the target. Furthermore, using the control policy learning by DRL, the UAV will achieve 58.14% less position error and 21.77% less system power.more » « less
-
A discrete time, optimal trajectory planning scheme for position trajectory generation of a vehicle is given here, considering the mission duration as a free variable. The vehicle is actuated in three rotational degrees of freedom and one translational degree of freedom. This model is applicable to vehicles that have a body-fixed thrust vector direction for translational motion control, including fixed-wing and rotorcraft unmanned aerial vehicles (UAVs), unmanned underwater vehicles (UUVs) and spacecraft. The lightweight scheme proposed here generates the trajectory in inertial coordinates, and is intended for real time, on-the-go applications. The unspecified terminal time can be considered as an additional design parameter. This is done by deriving the optimality conditions in a discrete time setting, which results in the discrete transversality condition. The trajectory starts from an initial position and reaches a desired final position in an unspecified final time that ensures the cost on state and control is optimized. The trajectory generated by this scheme can be considered as the desired trajectory for a tracking control scheme. Numerical simulation results validate the performance of this trajectory generation scheme used in conjunction with a nonlinear tracking control scheme.more » « less
-
Relative motion estimation of one rigid body with respect to another is a problem that has immediate applications to formations and maneuvers involving multiple unmanned vehicles or collision avoidance between vehicles. A finite-time stable observer for relative attitude estimation of a rigid object using onboard sensors on an unmanned vehicle, is developed and presented here. This observer assumes sensor inputs from onboard vision and inertial sensors, with the vision sensors measuring at least three points on the object whose relative locations with respect to a body-fixed frame on the object are also assumed to be known. In the absence of any measurement noise, the estimated relative attitude is shown to converge to the actual relative pose in a finite-time stable manner. Numerical simulations indicate that this relative attitude observer is robust to persistent measurement errors and converges to a bounded neighborhood of the true attitude.more » « less
